Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 100 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1255472 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0145. Min Act: -0.0006

Data Index: 680032 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0006

Data Index: 133875 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0006

Data Index: 972974 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0140. Min Act: -0.0006

Data Index: 261812 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0140. Min Act: -0.0006

Data Index: 300910 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0140. Min Act: -0.0006

Data Index: 388848 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1037615 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1331291 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0135. Min Act: -0.0006

Data Index: 123528 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0137. Min Act: -0.0006

Data Index: 991707 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0137. Min Act: -0.0006

Data Index: 461735 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0137. Min Act: -0.0006

Data Index: 350594 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1288940 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0132. Min Act: -0.0006

Data Index: 836008 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0006

Data Index: 274616 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0134. Min Act: -0.0006

Data Index: 774712 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0006

Data Index: 158076 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0133. Min Act: -0.0006

Data Index: 385463 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1189855 (C4 (Web Text))

Max Activating Token Index: 83